Products
In Lange et. al (2022) we quantified land-use intensity (LUI) and its key parameters - grazing intensity, mowing frequency and fertiliser application - across Germany. Key parameters were classified using Convolutional Neural Networks (CNN) and Copernicus Sentinel-2 satellite data with 20 m x 20 m spatial resolution. Predictions of LUI and its components were validated using comprehensive in situ grassland management data from the DFG Biodiversity Exploratories.
More information can be found in the related publication.
The data can be viewed in a >web service< (Link: https://www.ufz.de/land-use-intensity/en), as well as downloaded as GeoTiff-files for further analysis.
The Forest Condition Monitor is a project funded by the Helmholtz Association, located in the working group Land Cover and Dynamics. The monitor provides comprehensive information about forest condition for all forested areas in Germany. In addition, the project also derives other products such as dominant tree species, vegetation length (phenology), and future distribution of tree species under the influence of climate change.
Current satellite data is analysed in comparison with long-term observations to identify forest changes or anomalies. Subsequently, these anomalies are validated using forest condition surveys and damage mappings at selected observation sites. The monitor thus provides information for all forested areas in Germany. The maps from 2017 to 2022 show a significant increase in damaged forest areas, especially in central Germany, such as the Harz, Sauerland, and Saxon Switzerland regions, particularly from 2019. Various factors contribute to this, including heat, drought, pest infestations, and their combined effects, which damage the forests and also lead to secondary impacts such as windthrow and increased risk of forest fires. The scientific analysis using satellite data reveals, for the first time, the spatial dynamics of forest condition induced by climate change. In addition to forest condition, the project also derives other products such as dominant tree species, vegetation length (phenology), and future distribution of tree species under the influence of climate change. More information can be found in the related publication.
The data can be viewed in a web service, as well as downloaded as GeoTiff-files for further analysis.
Land-use / land-cover classification
In Preidl et. al (2020) we derived detailed crop type maps across Germany. Overcoming the obstacle of frequent cloud coverage in optical remote sensing data is essential for monitoring dynamic land surface processes from space. APiC, a novel adaptable pixel-based compositing and classification approach, is especially designed to use high resolution spatio-temporal space-borne data.
Here, pixel-based compositing is used separately for training data and prediction data. First, cloud-free pixels covered by reference data are used within adapted composite periods to compile a training dataset. The compiled training dataset contains samples of spectral reflectances for respective land cover classes at each composite period. For land cover prediction, pixel-based compositing is then applied region-wide. Multiple prediction models are used based on temporal subsets of the compiled training dataset to dynamically account for cloud coverage at pixel level. Thus we present a data-driven classification approach which is applicable in regions with different weather conditions, species composition and phenology.
The capability of our method is demonstrated by mapping 19 land cover classes across Germany for the year 2016 based on Sentinel-2A data. Since climatic conditions and thus plant phenology change on a large scale, the classification was carried out separately in six landscape regions of different biogeographical characteristics. The
study drew on extensive ground validation data provided by the federal states of Germany. For each landscape region, composite periods of different lengths have been established, which differ regionally in their temporal arrangement as well as in their total number, emphasising the advantage of a flexible regionalised classification procedure. Using a random forest classifier and evaluating outcomes with in dependent reference data, an overall accuracy of 88% was achieved, with particularly high classification accuracy of around 90% for the major land cover types. We found that class imbalances have significant influence on classification accuracy. Based on multiple temporal subsets of the compiled training dataset, over 10,000 random forest models were calculated and their performance varied considerably across and within landscape regions. The calculated importance of composite periods show that a high temporal resolution of the compiled training dataset is necessary to better capture the different phenology of land cover types.
In this study we demonstrate that APiC, due to its data-driven nature, is a very flexible compositing and classification approach making efficient use of dense satellite time series in areas with frequent cloud coverage.
Hence, regionalisation can be given greater focus in future broad-scale classifications in order to facilitate better integration of small-scale biophysical conditions and achieve even better results in detailed land cover mapping.
This data - along with tree species maps - can be viewed in a web service, as well as downloaded as GeoTiff-files for further analysis.
